# A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity

arXiv: https://arxiv.org/abs/2302.06015 · HTML: https://mlsanity.com/paper/2302.06015/

## Key facts

- Cited by 77 papers in the map (data through 14 Oct 2026).
- Builds on 66 of its 84 references that are in the map.
- First posted on arXiv 12 Feb 2023.

## Builds on (most cited first, 30 of 66)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Neural Tangent Kernel: Convergence and Generalization in Neural Networks](https://mlsanity.com/paper/1806.07572/) (2018)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [A Convergence Theory for Deep Learning via Over-Parameterization](https://mlsanity.com/paper/1811.03962/) (2018)
- [Gradient Descent Provably Optimizes Over-parameterized Neural Networks](https://mlsanity.com/paper/1810.02054/) (2018)
- [Universal Transformers](https://mlsanity.com/paper/1807.03819/) (2018)
- [Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks](https://mlsanity.com/paper/1901.08584/) (2019)
- [Twins: Revisiting the Design of Spatial Attention in Vision Transformers](https://mlsanity.com/paper/2104.13840/) (2021)
- [Deep Interest Network for Click-Through Rate Prediction](https://mlsanity.com/paper/1706.06978/) (2017)
- [Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth](https://mlsanity.com/paper/2103.03404/) (2021)
- [Are Transformers universal approximators of sequence-to-sequence functions?](https://mlsanity.com/paper/1912.10077/) (2019)
- [Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations](https://mlsanity.com/paper/2202.07800/) (2022)
- [AdaViT: Adaptive Tokens for Efficient Vision Transformer](https://mlsanity.com/paper/2112.07658/) (2021)
- [Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers](https://mlsanity.com/paper/1811.04918/) (2018)
- [An Investigation of Why Overparameterization Exacerbates Spurious Correlations](https://mlsanity.com/paper/2005.04345/) (2020)
- [On the Relationship between Self-Attention and Convolutional Layers](https://mlsanity.com/paper/1911.03584/) (2019)
- [Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning](https://mlsanity.com/paper/2012.09816/) (2020)
- [Post-Training Quantization for Vision Transformer](https://mlsanity.com/paper/2106.14156/) (2021)
- [Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data](https://mlsanity.com/paper/1808.01204/) (2018)
- [Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks](https://mlsanity.com/paper/1905.13210/) (2019)
- [Online Decision Transformer](https://mlsanity.com/paper/2202.05607/) (2022)

## Built on by (most cited first, 30 of 77)

- [In-Context Convergence of Transformers](https://mlsanity.com/paper/2310.05249/) (2023)
- [Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer](https://mlsanity.com/paper/2305.16380/) (2023)
- [Linear attention is (maybe) all you need (to understand transformer optimization)](https://mlsanity.com/paper/2310.01082/) (2023)
- [White-Box Transformers via Sparse Rate Reduction](https://mlsanity.com/paper/2306.01129/) (2023)
- [Transformers as Support Vector Machines](https://mlsanity.com/paper/2308.16898/) (2023)
- [Max-Margin Token Selection in Attention Mechanism](https://mlsanity.com/paper/2306.13596/) (2023)
- [JoMA: Demystifying Multilayer Transformers via JOint Dynamics of MLP and Attention](https://mlsanity.com/paper/2310.00535/) (2023)
- [On the Role of Attention in Prompt-tuning](https://mlsanity.com/paper/2306.03435/) (2023)
- [Why Larger Language Models Do In-context Learning Differently?](https://mlsanity.com/paper/2405.19592/) (2024)
- [Memorization Capacity of Multi-Head Attention in Transformers](https://mlsanity.com/paper/2306.02010/) (2023)
- [What can a Single Attention Layer Learn? A Study Through the Random Features Lens](https://mlsanity.com/paper/2307.11353/) (2023)
- [Attention with Markov: A Framework for Principled Analysis of Transformers via Markov Chains](https://mlsanity.com/paper/2402.04161/) (2024)
- [When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers](https://mlsanity.com/paper/2504.10957/) (2025)
- [On the Optimization and Generalization of Multi-head Attention](https://mlsanity.com/paper/2310.12680/) (2023)
- [Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks](https://mlsanity.com/paper/2306.04073/) (2023)
- [How Do Nonlinear Transformers Learn and Generalize in In-Context Learning?](https://mlsanity.com/paper/2402.15607/) (2024)
- [From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers](https://mlsanity.com/paper/2402.13512/) (2024)
- [Mechanics of Next Token Prediction with Self-Attention](https://mlsanity.com/paper/2403.08081/) (2024)
- [Graph Transformers: A Survey](https://mlsanity.com/paper/2407.09777/) (2024)
- [Transformers Learn to Implement Multi-step Gradient Descent with Chain of Thought](https://mlsanity.com/paper/2502.21212/) (2025)
- [Implicit Bias and Fast Convergence Rates for Self-attention](https://mlsanity.com/paper/2402.05738/) (2024)
- [A phase transition between positional and semantic learning in a solvable model of dot-product attention](https://mlsanity.com/paper/2402.03902/) (2024)
- [Transformers on Markov Data: Constant Depth Suffices](https://mlsanity.com/paper/2407.17686/) (2024)
- [In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness](https://mlsanity.com/paper/2402.11639/) (2024)
- [Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot](https://mlsanity.com/paper/2406.06893/) (2024)
- [Federated Learning from Vision-Language Foundation Models: Theoretical Analysis and Method](https://mlsanity.com/paper/2409.19610/) (2024)
- [Bypassing the Exponential Dependency: Looped Transformers Efficiently Learn In-context by Multi-step Gradient Descent](https://mlsanity.com/paper/2410.11268/) (2024)
- [Provably learning a multi-head attention layer](https://mlsanity.com/paper/2402.04084/) (2024)
- [A Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts](https://mlsanity.com/paper/2405.16646/) (2024)
- [Dissecting Chain-of-Thought: Compositionality through In-Context Filtering and Learning](https://mlsanity.com/paper/2305.18869/) (2023)

## Abstract (arXiv)

Vision Transformers (ViTs) with self-attention modules have recently achieved great empirical success in many vision tasks. Due to non-convex interactions across layers, however, theoretical learning and generalization analysis is mostly elusive. Based on a data model characterizing both label-relevant and label-irrelevant tokens, this paper provides the first theoretical analysis of training a shallow ViT, i.e., one self-attention layer followed by a two-layer perceptron, for a classification task. We characterize the sample complexity to achieve a zero generalization error. Our sample complexity bound is positively correlated with the inverse of the fraction of label-relevant tokens, the token noise level, and the initial model error. We also prove that a training process using stochastic gradient descent (SGD) leads to a sparse attention map, which is a formal verification of the general intuition about the success of attention. Moreover, this paper indicates that a proper token sparsification can improve the test performance by removing label-irrelevant and/or noisy tokens, including spurious correlations. Empirical experiments on synthetic data and CIFAR-10 dataset justify our theoretical results and generalize to deeper ViTs.